TSE-An AI engineering assistant for D365 F&O
Works in Visual Studio, VS Code / Copilot, Cursor, Claude Code, and Claude Desktop.
Built for the way D365 work actually gets done
One assistant, three audiences. Every capability below runs through governed, audited tools — grounded in your environment, never in guesses.
The whole implementation loop — not just code suggestions
Hand it a requirement and it works the way a senior X++ developer does: understand first, change deliberately, build, fix, and prove. Interactively with a review gate on every write — or fully automatic when you choose.
Start from the requirement
A prompt, a Markdown spec, a Word document or PDF — dropped into the chat client you already use (GitHub Copilot, Claude, Cursor, …). The assistant implements from what the requirement actually says.
Understand the system before touching it
It studies the existing implementation — standard and custom — follows the dependency chain across classes and methods, and runs find-references over the whole AOT, so a change in one method accounts for every caller, override, and extension point. No guessing.
Author the change
It creates or modifies the objects the requirement needs — classes, tables, forms, extensions, EDTs, enums, menu items — including labels, added to your existing label file or a newly scaffolded one.
Land it in your model and project
Everything is written into your custom model and added to your Visual Studio project automatically — atomic writes, a Change ID on every apply, undo with full reverse diffs.
Build through the real toolchain
It compiles the project — or the whole model when the change calls for it — and reports honestly: "X++ compile ran" vs "nothing changed, binaries untouched".
Read the errors, fix, rebuild
Compiler output is read and traced back to the objects; the assistant iterates until the build is green.
Best practices, enforced
It runs BP checks over the new and modified objects and resolves the violations its own change introduced.
Prove it with tests
It writes SysTest classes in your dedicated test model, stages the records the tests need through governed SQL data access, runs the suite, and grades the outcome from the results XML. Credentials are never hardcoded or pasted in plain text — they're picked up from the environment's own configuration and sealed in the OS secret store.
Supervised or automatic — your call
Approve each step, or select automatic mode and let the assistant drive the loop end-to-end. The gates, the Change IDs, and the audit trail are identical either way.
Tools-only, by contract
The assistant's working instructions bind it to its governed tools — no direct XML edits on disk that would dodge the audit log, the project wiring, or undo.
The same rules in every client
Instruction packs — naming, extension-first patterns, workflow, testing, domain — are wired into Visual Studio/Copilot, VS Code, Cursor, Claude Code and Claude Desktop at install, so every MCP-capable client works to the same agreement.
It learns your environment
During implementation it proposes saving what mattered — conventions, gotchas, environment quirks — to local memory, so the next task starts smarter.
Answers and evidence — without waiting on a developer
For consultants and support users: the same grounded assistant, pointed at the questions the business actually asks — with independent, governed data access instead of "raise a ticket and wait for a script". In the chat you already use, with the LLM you already have — Claude, GitHub Copilot, Cursor, and any MCP-capable client.
Understand any object or process in plain language
How a posting works, where a field comes from, what a customization changed — explained from the environment's real metadata and code, with sources cited.
Work with data independently
Inspect records, and create or modify the test records needed to replicate an issue or stage a scenario — no developer, no ad-hoc scripts. Every operation is entitlement-gated and audited.
Security, actually answered
What can this user do and why? Where do roles and duties overlap? What's the security difference between these two users? Segregation-of-duty exposure, surfaced from the environment's real security artifacts.
Compare environments
Why does the process behave differently in UAT and PROD? Ask for the configuration difference for a feature, implementation, or process across your registered environments.
From requirement to FDD
Generate functional design documents grounded in the objects the change will actually touch — a running start for every CR.
Trace processes end-to-end
Menu item → form → data sources → tables → posting chain, walked through the real dependency graph, not from documentation memory.
Drop in a screenshot, get grounded guidance
Support users drag a screenshot of the error or form into the chat and ask. The assistant reads it, matches it against the environment's real objects, configuration, and security, and explains what it means and where to look.
Super-user seats: zero infrastructure
Support and super-user seats pull a published, source-stripped index — no metadata root, no build, read-first with any write surface limited by policy. First-line answers from the environment itself.
Sofiaby TSE-Assistant
consultant · read-only
Environment ▾⚙ Settings🧠 memory
I help you make sense of your Dynamics 365 F&O system in plain business language — how processes work, who can do what, and your live data. Ask me anything, or drop in a screenshot.
From zero to first answer in minutes
No infrastructure to run — install once and ask.
Sign in & pick your tier
Individuals sign in with GitHub or Microsoft and start a 16-day trial — no card. Team members sign in with Microsoft SSO; their admin's registration token activates the install.
Run the installer
A self-contained download bundles everything. It indexes your PackagesLocalDirectory — reusing a shared standard prebuilt where possible so only your customizations are extracted locally — and wires up your IDEs automatically, merging with any MCP servers you already have. On a live dev box, close Visual Studio first, and for the fastest build stop SQL Server, the AOS Batch service and Management Reporter while it runs — the index build competes with them for disk. The installer detects them and can stop & restart them for you.
Ask in your IDE
Open Copilot/Claude in agent mode and ask about CustTable, scaffold a CoC extension, or trace a relation — instantly, against your environment.
Hardened the hard way: every release is regression-tested by an adversarial AI tester running versioned manifests against a real D365 dev environment — reads, writes, builds, syncs and test runs verified against exact repros before anything ships.
Get started
Pick the path that fits you.
Just me
For independent consultants & contractors. Sign in, pick add-ons, start a 16-day free trial. No admin, no card to start.
Sign in with GitHub Sign in with MicrosoftAfter sign-in you choose add-ons and get an activation code for the installer.
My team / company
Central seats, a shared dashboard, and audit. Your admin provisions seats and hands out registration tokens.
Open the team dashboardAdmins sign in here to manage seats and generate registration tokens; members paste a token when installing.